analiza aiqbench
This research introduces SA-LIVO, an advanced odometry system that optimally fuses LiDAR, inertial, and visual data by addressing sensor-specific degeneracies through subspace-aware information fusion. By dynamically gating eigendirections in the joint information matrix rather than applying isotropic gains, the method maintains accuracy under concurrent degradation while significantly reducing computational overhead on embedded hardware without GPUs. The approach represents a meaningful step forward for robotics navigation systems requiring robust performance across diverse environmental conditions where individual sensors may fail independently.
SA-LIVO: Efficient LiDAR-Inertial-Visual Odometry with Subspace-Aware Degeneracy Handling
arXiv:2606.25699v2 Announce Type: replace Abstract: Tightly coupled LiDAR-inertial-visual odometry (LIVO) fuses geometric depth with visual measurements, but its exteroceptive sensors fail independently: LiDAR when scan geometry is under-constrained, vision under poor illumination or texture absence. Existing countermeasures (binary degeneracy detection, covariance inflation, scene-level quality gating) act at the modality level, so a single isotropic gain sends visual residuals into directions LiDAR already constrains well and cannot concentrate them where constraints are deficient. We propose Subspace-Aware LiDAR-inertial-visual odometry (SA-LIVO), whose Subspace-Aware Information Fusion (SAIF) eigendecomposes the joint LiDAR-visual information matrix and gates each eigendirection by a single-threshold linear clamp, attenuating low-amplitude directions while passing well-observed ones at full strength; robust per-residual gating and a scene-level quality factor screen corrupted measurements. LiDAR and visual residuals share one invariant extended Kalman filter (InEKF) loop and linearization point, letting photometric Jacobians be assembled once and reused across iterations. On 29 public-benchmark sequences (HILTI'22, Newer College Dataset (NCD), Oxford Spires), plus additional concurrent-degradation scenarios, SA-LIVO matches the strongest baselines in accuracy and stays bounded where competing systems diverge. On the HILTI'22 subset that every baseline completes, it averages 12.3 ms per frame on a laptop CPU and 26.8 ms on an embedded ARM board without GPU, at 3.6-6.3x lower peak memory.
Abstract:Tightly coupled LiDAR-inertial-visual odometry (LIVO) fuses geometric depth with visual measurements, but its exteroceptive sensors fail independently: LiDAR when scan geometry is under-constrained, vision under poor illumination or texture absence. Existing countermeasures (binary degeneracy detection, covariance inflation, scene-level quality gating) act at the modality level, so a single isotropic gain sends visual residuals into directions LiDAR already constrains well and cannot concentrate them where constraints are deficient. We propose Subspace-Aware LiDAR-inertial-visual odometry (SA-LIVO), whose Subspace-Aware Information Fusion (SAIF) eigendecomposes the joint LiDAR-visual information matrix and gates each eigendirection by a single-threshold linear clamp, attenuating low-amplitude directions while passing well-observed ones at full strength; robust per-residual gating and a scene-level quality factor screen corrupted measurements. LiDAR and visual residuals share one invariant extended Kalman filter (InEKF) loop and linearization point, letting photometric Jacobians be assembled once and reused across iterations. On 29 public-benchmark sequences (HILTI'22, Newer College Dataset (NCD), Oxford Spires), plus additional concurrent-degradation scenarios, SA-LIVO matches the strongest baselines in accuracy and stays bounded where competing systems diverge. On the HILTI'22 subset that every baseline completes, it averages 12.3 ms per frame on a laptop CPU and 26.8 ms on an embedded ARM board without GPU, at 3.6-6.3x lower peak memory.
Robotics (cs.RO)
arXiv:2606.25699 [cs.RO]
(or arXiv:2606.25699v2 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.25699 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 292 cuvinte
Subiecte conexe
Dynamic-LIVO: A Dynamic-Aware LiDAR-Inertial-Visual Odometry System Using Spatio-Temporal Normals
arXiv · 18 sept. 2026
KILVO: Kinematic-Inertial-LiDAR-Visual Odometry with Robust Multimodal Adaptation for Humanoid Robots
arXiv · 7 aug. 2026
FIRE-LIVWO: Robust LiDAR-Inertial-Visual-Wheel Odometry via Failure-Immune mmWave Radar Enhancement
arXiv · 7 sept. 2026
HexVIO: Towards All-Day Stereo-Inertial Tracking Through Commodity DSPs
arXiv · 5 oct. 2026